Improved Dimension Dependence for Bandit Convex Optimization with Gradient Variations

arXiv:2602.04761 · cs.LG, stat.ML · Submitted 2026-02-04 · Read on arXiv

cs.LG, stat.ML

Submitted: 2026-02-04

Updated: 2026-09-08

Comments: ICML 2026

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Regret — 137× in this paper · explained in 3 episodes
• Bandit Convex Optimization — 44× in this paper
• Loss Function — 11× in this paper · explained in 2 episodes
• Online Convex Optimization — 9× in this paper
• Geometric Distribution — 6× in this paper · explained in 2 episodes
• Bandit Linear Optimization — 5× in this paper
• Adaptivity — 3× in this paper · explained in 1 episode
• International Conference on Machine Learning — 2× in this paper
• Non-stationarity — 2× in this paper · explained in 2 episodes
• Optimistic Online Gradient Descent — 2× in this paper
• ACM-SIAM Symposium on Discrete Algorithms — 1× in this paper
• Accuracy — 1× in this paper · explained in 1 episode
• Adaptive Algorithm — 1× in this paper · explained in 1 episode
• Annual Conference on Learning Theory — 1× in this paper
• Decoupling — 1× in this paper · explained in 2 episodes
• Ensemble Approach — 1× in this paper · explained in 3 episodes
• Minimax Regret — 1× in this paper · explained in 2 episodes
• Minimax optimality — 1× in this paper · explained in 2 episodes
• Nash Equilibrium — 1× in this paper · explained in 2 episodes

Sources

• Non-Stationary Bandit Convex Optimization: An Optimal Algorithm with Two-Point Feedback
• Bandit Convex Optimisation
• Online Learning: A Modern Introduction Using Convex Optimization

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks